Morgan(@morganlinton):I'm going to hold off on testing GPT 5.6 Sol in VulcanBench as there seems to be a small bug that might be impacting token use. Since VulcanBench scores models based on accuracy and token efficiency, I want to make sure to give GPT 5.6 Sol a fair shot. That being said, so far I am really liking the model, it's a great model, and the Codex team is always super fast at responding to and fixing stuff like this, so I still think there's a chance I can benchmark it this weekend!

2026.07.10 15:37

I'm going to hold off on testing GPT 5.6 Sol in VulcanBench as there seems to be a small bug that might be impacting token use. Since VulcanBench scores models based on accuracy and token efficiency, I want to make sure to give GPT 5.6 Sol a fair shot. That being said, so far I am really liking the model, it's a great model, and the Codex team is always super fast at responding to and fixing stuff like this, so I still think there's a chance I can benchmark it this weekend!

Peter Dedene@dedene

2026.07.10 08:56

If you're wondering why GPT-5.6 Sol with subagents in the Codex CLI burns through your usage so fast, there seems to be a bug. 👀 It can't spawn smaller subagents for basic exploration or web research and forces Sol for everything. Which is annoying because as with Fable, I'd love the Advisor / Executor workflow. Anyone else seeing this too? Workaround for now: add this to your ~/.codex/config.toml: [features.multi_agent_v2] hide_spawn_agent_metadata = false tool_namespace = "agents"